Related papers: Automated QoR improvement in OpenROAD with coding …

Data encoding is a common and central operation in most data analysis tasks. The performance of other models downstream in the computational process highly depends on the quality of data encoding. One of the most powerful ways to encode…

Edge intelligence delivers low-latency inference, yet most edge analytics remain hard-coded and must be redeployed as conditions change. When data patterns shift or new questions arise, engineers often need to write new scripts and push…

End-to-end approaches to autonomous driving commonly rely on expert demonstrations. Although humans are good drivers, they are not good coaches for end-to-end algorithms that demand dense on-policy supervision. On the contrary, automated…

Autonomous driving (AD) technology promises to revolutionize daily transportation by making it safer, more efficient, and more comfortable. Their role in reducing traffic accidents and improving mobility will be vital to the future of…

We present a novel autonomous driving framework, DualAD, designed to imitate human reasoning during driving. DualAD comprises two layers: a rule-based motion planner at the bottom layer that handles routine driving tasks requiring minimal…

Pre-trained on massive amounts of code and text data, large language models (LLMs) have demonstrated remarkable achievements in performing code generation tasks. With additional execution-based feedback, these models can act as agents with…

In this paper, we present a work in progress about a deep learning based approach for automatic code optimization in polyhedral compilers. The proposed technique explores combinations of affine and non-affine loop transformations to find…

This study explores a novel approach to enhance the performance of Large Language Models (LLMs) through the optimization of input data within prompts. While previous research has primarily focused on refining instruction components and…

Low Rank Decomposition of matrix - splitting a large matrix into a product of two smaller matrix offers a means for compression that reduces the parameters of a model without sparsification, and hence delivering more speedup on modern…

Mixture of Experts (MoE) architectures increase large language model scalability, yet their performance depends on the router module that moves tokens to specialized experts. Bad routing can load imbalance and reduced accuracy. This project…

Software logging is critical for system observability, yet developers face a dual crisis of costly overlogging and risky underlogging. Existing automated logging tools often overlook the fundamental whether-to-log decision and struggle with…

Powerful large language models (LLMs) from different providers have been expensively trained and finetuned to specialize across varying domains. In this work, we introduce a new kind of Conductor model trained with reinforcement learning to…

We present a general framework for modifying quantum approximate optimization algorithms (QAOA) to solve constrained network flow problems. By exploiting an analogy between flow constraints and Gauss's law for electromagnetism, we design…

In the first half of 2025, coding agents have emerged as a category of development tools that have very quickly transitioned to the practice. Unlike ''traditional'' code completion LLMs such as Copilot, agents like Cursor, Claude Code, or…

Autonomous Driving (AD) systems have made notable progress, but their performance in long-tail, safety-critical scenarios remains limited. These rare cases contribute a disproportionate number of accidents. Vision-Language Action (VLA)…

Timely, personalized feedback is essential for students learning programming. LLM-powered tools like ChatGPT offer instant support, but reveal direct answers with code, which may hinder deep conceptual engagement. We developed CodeAid, an…

Electrical design automation (EDA) techniques have deeply influenced the computer hardware design, especially in the field of very large scale Integration (VLSI) circuits. Particularly, the popularity of FPGA, ASIC and SOC applications have…

Open-ended self-improving agents can autonomously modify their own structural designs to advance their capabilities and overcome the limits of pre-defined architectures, thus reducing reliance on human intervention. We introduce…

Code completion is a valuable topic in both academia and industry. Recently, large-scale mono-programming-lingual (MonoPL) pre-training models have been proposed to boost the performance of code completion. However, the code completion on…

With the proliferation of edge AI applications, satisfying user quality of experience (QoE) requirements, such as model inference latency, has become a first class objective, as these models operate in resource constrained settings and…